Gemini AI Studio
Configuration
credentials:
- name: "gemini_studio"
type: "gemini"
api_key: "os.environ/GEMINI_API_KEY"
base_url: "https://generativelanguage.googleapis.com"
rpm: 60
tpm: -1
Required Fields
| Field | Description |
|---|---|
api_key |
Google AI Studio API key (supports os.environ/VAR_NAME) |
base_url |
API base URL (https://generativelanguage.googleapis.com) |
API Key Setup
- Go to Google AI Studio
- Create an API key
- Set it in your environment or config:
OpenAI-Compatible API
Gemini AI Studio uses the same converter as Vertex AI. All parameter mappings, tool types, thinking configuration, content types, structured output, streaming, and token counting work identically.
See the Vertex AI documentation for the full reference on:
- Supported parameters
- Tool calling
- Reasoning / Thinking
- Content types (text, images, audio, video)
- Audio output
- Structured output
- Image generation
- Streaming